US 12,302,004 B2
Image recognition device and image recognition method
Kazuyuki Okuike, Kanagawa (JP)
Assigned to Sony Semiconductor Solutions Corporation, Kanagawa (JP)
Appl. No. 17/603,138
Filed by Sony Semiconductor Solutions Corporation, Kanagawa (JP)
PCT Filed May 18, 2020, PCT No. PCT/JP2020/019587
§ 371(c)(1), (2) Date Oct. 12, 2021,
PCT Pub. No. WO2020/241336, PCT Pub. Date Dec. 3, 2020.
Claims priority of application No. 2019-101728 (JP), filed on May 30, 2019.
Prior Publication US 2022/0201183 A1, Jun. 23, 2022
Int. Cl. H04N 23/73 (2023.01); G01S 17/86 (2020.01); G01S 17/894 (2020.01); G06V 10/82 (2022.01); H04N 23/84 (2023.01)
CPC H04N 23/73 (2023.01) [G01S 17/86 (2020.01); G01S 17/894 (2020.01); G06V 10/82 (2022.01); H04N 23/843 (2023.01)] 12 Claims
OG exemplary drawing
 
1. An image recognition device comprising:
an image sensor including a pixel array with pixels arrayed two-dimensionally, the pixels including a first pixel, a second pixel and a third pixel in a same light receiving area, the first pixel corresponding to a first color, the second pixel corresponding to a second color, and the third pixel corresponding to a third color, each of the pixels including a first light receiving element and a second light receiving element for a corresponding color of the pixel and an infrared light receiving element, the first light receiving element being configured to have a first exposure time, the second light receiving element being configured to have a second exposure time that is different from the first exposure time,
a memory storing a program, and
a processor configured to execute the program to perform operations comprising:
receiving signals from the image sensor based upon each of the first, second and third pixels;
determining whether a subject is recognized from the signals of each of the first, second and third pixels separately from synthesizing an image data from the signals;
generating the image data from the signals received from the image sensor;
in a case of recognizing the subject, outputting a recognition result of the subject and the image data to a subsequent device; and
in a case of not recognizing the subject, outputting information indicating that the subject is not recognized to the subsequent device.